dsh-routing-suite

dsh-routing-suite, injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23).

Runssource: GitHubJavaScriptMITcommit 195273352f23

JavaScript, MIT licensed. The project labels itself: ai agents, cordis, deepseek harness, dsh and dsh plugin.

dsh-routing-suite runs. An Argusic agent installed it in 6.2 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

All 116 tests pass across root-package (2/2), preset (50/50 + 1/1 selftest), and graded (63/63) suites using Node.js v22.12.0; injector lib/ built successfully with tsdown.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.09 (measured)
recorded runs
1
last tested
stars
6,996
forks
182
open issues
101
watchers
17
size
1 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing dsh-routing-suite, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • System Node.js v18.19.1 too old (project requires >=22); injector build (tsdown/rolldown) fails without native binding optional deps3.5 minutes
  • Root package test 2 (pack --dry-run) fixture missing injector/scripts/prepare.mjs, and npm 10+ interleaves prepare stdout with JSON output2.5 minutes
Install time
6 minutes
Cold machine to finish
9 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
node --test with all 6 test files: test/root-package-prepare.test.mjs, preset/router.test.mjs, preset/router.integration.test.mjs, preset/router-standard/router-bootstrap-v34.selftest.mjs, graded/tests/mode-state.test.mjs, graded/tests/tools.test.mjs, graded/tests/inject-text.test.mjs, 116 tests passed, 0 failed, 0 skipped, 982ms duration
Model tokens used
105,645
Exact commit tested
195273352f23
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

ok 113 - runtimeCallable: 与 SDK 绑定同源(v1.11)
ok 114 - v1.16: muteAwareList/isMemoryTool + external evidence
ok 115 - the root package runs the injector prepare hook for git installs
ok 116 - the prepared injector entry points are included in the package
# tests 116
# pass 116
# fail 0
# duration_ms 964.73583
All 116 tests pass across all three components. Let me compile the final report now.
tokens used
105,645
All 116 tests pass across all three components. Let me compile the final report now.

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Reached a running state on a clean machine, with the session recorded.
  • Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Took 6.2 minutes to install, slower than the median of the 29 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 30 ai-agents projects Argusic has installed and timed, dsh-routing-suite was the 17th fastest to reach a running state, and 20 of 30 reached one at all.

What it is a reasonable choice for

  • Trying it on a laptop or a small server: it reached a running state without a GPU.
  • A quick evaluation: it was running 6.2 minutes after the clone.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.09

Topics (from GitHub)

ai-agentscordisdeepseek-harnessdshdsh-plugin

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/dsh-routing-suite.svg)](https://argusic.com/subject/dsh-routing-suite)

Questions

Does dsh-routing-suite run?
Yes. dsh-routing-suite runs. Argusic installed and launched it on a clean machine in 6 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test dsh-routing-suite?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 195273352f23. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test dsh-routing-suite?
The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does dsh-routing-suite take to install?
6.2 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does dsh-routing-suite need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing dsh-routing-suite?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does dsh-routing-suite compare with the alternatives?
Of the 30 ai-agents projects Argusic has installed and timed, dsh-routing-suite was the 17th fastest to reach a running state, and 20 of 30 reached one at all.
Where is the evidence for dsh-routing-suite?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion